Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chrisallenlane/claude-swe-workflows --skill bug-huntgit clone --depth 1 https://github.com/chrisallenlane/claude-swe-workflowsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/bug-hunt)<a href="https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/bug-hunt"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/bug-hunt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/bug-hunt"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/bug-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.04348 |
| Opus 5 | $0.00030 | $0.02174 |
| Sonnet 5 | $0.00012 | $0.00870 |
| Haiku 4.5 | $0.00006 | $0.00435 |
Grade A, and why
bug-hunt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Hunt — Proactive Bug Discovery
Systematically hunts for bugs before they reach users. An assessor analyzes the codebase to identify high-risk hotspots by cross-referencing code complexity, test coverage gaps, and structural risk factors. Focused hunters then deep-dive into each hotspot, writing reproducing tests to validate or invalidate suspected bugs.
This is deliberately thorough. Each suspected bug gets a reproducing test — no speculative reports. The goal is confirmed findings with evidence, not a noisy list of maybes.
Advisory only. The skill produces findings and proposes tickets; it does not implement fixes. The cognitive seam between "find bug" and "fix bug" is wide enough that mixing them under one workflow degrades both — investigation pressure shouldn't bias the hunters toward bugs they could easily fix, and remediation requires fresh reasoning the hunters aren't currently in. Tickets capture findings durably across that seam and compose with /implement and /implement-project for remediation. The reproducing tests serve as acceptance criteria — the fix is done when the test passes.
Workflow Overview
┌──────────────────────────────────────────────────────┐
│ BUG HUNT WORKFLOW │
├──────────────────────────────────────────────────────┤
│ 1. Determine scope │
│ 2. Spawn assessor (risk analysis) │
│ └─ Output: ranked hotspot list + coverage map │
│ 3. For each hotspot: │
│ └─ Spawn hunter (investigation + repro tests) │
│ └─ Prior findings passed to subsequent hunters │
│ 4. Synthesize findings │
│ 5. Present consolidated findings to user │
│ 6. Cut tickets + commit reproducing tests │
│ (proposed structure; operator-approved) │
│ 7. (If tickets declined) commit reproducing tests │
│ standalone for the coverage benefit │
└──────────────────────────────────────────────────────┘
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 433 lines · 59 tokens per session scan A 237f2c66653f
bug-hunt is a skill published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 4,348 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
ai-slop-cleaner
Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.
code-review
Review code changes for concrete defects.
oracle-debug
Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this", "diagnose this", unexpected behavior, build failures, integration issues, or performance regressions. Find root cause before a permanent corrective fix; contain urgent harm safely first.
scrutinize
Ultrathink principal-engineer review gate. Runs a Validate-Identify-Improve-Adjust (VIIA) pass over a target - a plan awaiting approval, just-executed work, a specific file or directory, or the entire workspace - then runs an adversarial refutation layer (Phase 2.5) with cross-family judge rotation (Claude and Kimi…
anti-stub-scan
Scan a diff for stub patterns and TODO markers.